Entrpi / ds4-on-spark
Entrpi/ds4, a Blackwell CUDA perf fork of antirez/ds4 on NVIDIA DGX Spark: one-command install, ~3x upstream prefill, ~1.5x decode, DSpark, and full continuous batch support
Why this job: topics: gguf, inference
What it does
- POST /v1/chat/completions and POST /v1/completions (OpenAI)
- POST /v1/responses (OpenAI Responses, used by Codex)
- POST /v1/messages (Anthropic Messages, used by Claude Code)
- GET /v1/models, GET /metrics (Prometheus), GET /v1/stats (live status board)
Get started
curl -sSL https://raw.githubusercontent.com/entrpi/ds4-on-spark/main/install.sh | bash -s -- --start - Maintenance
- Active
- Last commit 2 months ago
- Stars
- 414
- +2 this week
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Shell
- 69% of the code
Is it looked after?
- Contributors
- 1
- Last 90 days
- Issues
- 70% closed
- 7 still open
- Pull requests
- 0 merged
- 0 waiting
- Releases
- None
- Never published
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| Avarok-Cybersecurity / atlas | 714 | 47 days ago | AGPL-3.0 | No downloads |
| vllm-project / vllm | 96,588 | today | Apache-2.0 | Mac, Linux |
| raullenchai / twinspark | 176 | 2 months ago | MIT | No downloads |
More: languages, topics and project record
Languages
- Shell 69%
- Python 26%
- Cuda 5%
Topics
- benchmark
- cuda
- deepseek-v4-flash
- dgx-spark
- gb10
- gguf
- inference
- llm
- moe
Project record
- JobLocal LLMs
- StatusListed
- Commits63
- Forks30
- Watching12
- Stars in 28 days+7
- CreatedMay 12, 2026
- First seen by usNov 7, 2026
- CheckedNov 7, 2026